adding other category

moderne_visualizations_misc/comment_language_distribution.ipynb

@@ -31,9 +31,18 @@
     "    #get counts of each language\n",
     "    language_counts = dict(df[\"language\"].value_counts())\n",
     "\n",
+    "    #remove all the smaller percentages of languages and merge them into a category called other\n",
+    "    sum_value = sum(language_counts.values())\n",
+    "    language_counts_w_other = {\"other\":0}\n",
+    "\n",
+    "    for lang, value in language_counts.items():\n",
+    "        if value/sum_value<=0.05:\n",
+    "            language_counts_w_other[\"other\"]=language_counts_w_other[\"other\"]+value\n",
+    "        else:\n",
+    "            language_counts_w_other[lang]=value\n",
     "    # plot\n",
     "    fig, ax = plt.subplots()\n",
-    "    ax.pie(language_counts.values(), labels=language_counts.keys(),  colors=colors.qualitative(), frame=False, autopct='%1.1f%%')\n",
+    "    ax.pie(language_counts_w_other.values(), labels=language_counts_w_other.keys(),  colors=colors.qualitative(), frame=False, autopct='%1.1f%%')\n",
     "    plt.axis('off')\n",
     "    plt.tight_layout()\n",
     "    plt.show()\n",